Development of algorithmic algebra tools to design parallel programs using heuristics

The paper proposes a new approach and a system to develop parallel algorithms based on the joint use of the algebraic-algorithmic methodology of specification and development of programs and non-algorithmic (heuristic) techniques for code generation. The algebraic part of the methodology provides the formalized process of parallel program design through high-level algebraic-algorithmic specifications and automating transformations up to program code in a standard programming language. The heuristic part of the system is the dynamic adjustment of program code to a target platform and its optimization using self-learning code generation and heuristic technologies.